Optimizing I/O for Data‑Intensive Analytics in Cloud‑Native Environments: Insights from Uber’s Presto Deployment

This whitepaper explores the industry trend of migrating data‑intensive analytics applications from on‑premises environments to cloud‑native platforms, emphasizing the unique cost model of cloud storage and its implications for performance optimization.

Through an empirical study of Uber’s production Presto workload, the authors discover that more than 50 % of data accesses are smaller than 10 KB and over 90 % are under 1 MB, indicating a highly fragmented access pattern that incurs significant storage API call costs in the cloud.

The paper presents a case‑study‑driven analysis of traditional I/O optimization techniques, demonstrating that they often ignore the financial overhead of storage API interactions, which can lead to unexpectedly high expenses when applications are migrated to cloud environments.

Based on these findings, the authors propose a set of cloud‑aware I/O design principles and strategies aimed at improving cost‑performance ratios for data‑intensive workloads in cloud‑native settings.

Readers will gain a concrete framework for designing efficient I/O solutions tailored to cloud storage economics, providing a foundation for further research and practical implementation.